RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
Paper
•
2503.01820
•
Published
•
2
•
3
Jaehong Yoon
jaehong31
AI & ML interests
None yet
Recent Activity
authored
a paper
about 13 hours ago
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for
Efficient and Enhanced Video Reasoning
authored
a paper
about 13 hours ago
Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding
authored
a paper
about 13 hours ago
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert
Aggregation
Organizations
commented
a
paper
10 months ago